Axelera AI Secures $250 Million to Scale Energy-Efficient Chips for Edge Computing

BlackRock Backs Dutch Chipmaker Axelera AI in $250 Million Round

Dutch chipmaker Axelera AI raised more than $250 million from investors including BlackRock Inc. to make power-efficient semiconductors that are designed to run artificial intelligence models after they've been trained. The round, which confirms a Bloomberg report last year, was led by European venture capital fund Innovation Industries, Axelera said in a statement Tuesday. It included participation from existing investors like Samsung Catalyst and new ones like BlackRock. Axelera AI makes chips for inference, the process of running AI models in real-world applications. While much inference still takes place in the cloud, it can also be deployed locally on devices such as phones or security cameras. The firm's chips are designed for such "edge" applications, which aim to reduce reliance on large data centers powered by GPUs such as those made by Nvidia Corp. While Nvidia's chips are still the dominant products for training and running AI models, the inference market is expanding rapidly as companies monetize their AI investments. Last year, Nvidia reached a licensing deal with AI startup Groq, which produces low-latency chips similar to the ones Axelera focuses on. Nevada-based startup Positron, which makes AI chips for inference, this month raised $230 million in a funding round. Axelera has "a large pipeline of opportunities that require investments and this pipeline is increasing," Chief Executive Officer Fabrizio Del Maffeo said in an interview with Bloomberg. Customers are looking for more accessible compute, efficiency and a way to reduce spending on costly AI infrastructure, he added. Axelera is headquartered in the Netherlands's Eindhoven region, which is also home to chip machine giant ASML Holding NV, Europe's most valuable company. Inference can run on a decentralized chip architecture that's less power hungry, Del Maffeo said. The intensive energy requirements of the large data centers needed to train AI models have come under scrutiny amid concerns about straining power grids and soaring energy costs for consumers. Axelera AI did not disclose a valuation in the latest round. It has attracted over $450 million in equity, grants and venture debt since incorporating in 2021. The firm's customer base has more than tripled in the past year, it said.

European AI chip startup Axelera raises additional $250 million

AMSTERDAM, Feb 24 (Reuters) - Axelera AI has secured $250 million in a funding round led by Innovation Industries that included BlackRock and SiteGround Capital as new investors, it said on Tuesday, marking one of the largest investments to date in a European AI chipmaking firm. CEO Fabrizio Del Maffeo said in a statement the company would use the money to expand manufacturing of its "Europa" chip, which it plans to launch before June, and to further develop software that makes using its chips easier for customers. Axelera, based in Eindhoven in the Netherlands, is one of the few companies in Europe that make specialised computer chips for AI applications. Its energy-efficient inference chips are used in industrial settings for running, not training, AI models. Since its founding in 2021, it has raised more than $450 million. Previous investors including Bitfury, Verve Investments, Samsung Electronics' (005930.KS), opens new tab Catalyst Fund, the European Innovation Council Fund and funds backed by the Belgian and Dutch governments also participated in the latest round. Axelera received a $66 million grant in March 2025 as part of a European Union project to develop an advanced chip dubbed "Titania" for use in supercomputing centres - also referred to as AI factories. That chip is expected in 2027. Reporting by Toby Sterling; editing by Barbara Lewis Our Standards: The Thomson Reuters Trust Principles., opens new tab

Edge AI chip startup Axelera AI raises $250M+ funding round - SiliconANGLE

Axelera AI BV, a Dutch supplier of artificial intelligence chips for edge devices, today announced that it has raised more than $250 million in funding. Amsterdam-based venture capital firm Innovation Industries led the investment. It was joined by BlackRock, Samsung Catalyst Fund and several others. Axelera AI's flagship product is an AI chip called Metis that can perform 214 trillion computations per second. The processor usually consumes about 10 watts, which makes it suitable for use in battery-powered connected devices. A warehouse robot, for example, could use an embedded Metis processor to run AI navigation software. Metis is powered by an architecture that Axelera AI calls digital in-memory computing, or D-IMC for short. It lowers power usage by limiting data movement inside the chip. AI processors usually store and process data using two different sets of circuits. Data has to be regularly shuffled between those circuits during processing, which consumes power. Axelera AI's D-IMC architecture uses SRAM, a high-speed memory variety, to store and process information in the same place. That reduces the need to move data between different sections of the chip and thereby lowers power usage. D-IMC organizes SRAM modules in a configuration known as a crossbar array. Such arrays can carry out calculations on vectors and matrices, the two basic units of data used by AI models. A vector is a single row of numbers while a matrix comprises several rows. "Data centers are hitting power and cooling limits, and as analytics move closer to where data is being created, edge AI solutions must operate within strict energy and bandwidth constraints," said Axelera AI co-founder and chief executive officer Fabrizio Del Maffeo. "We designed our architecture from the ground up to overcome these obstacles." Axelera AI ships Metis as part of two accelerator cards that customers can attach to their connected devices. The first card contains up to 4 chips and attaches to the host system via a PCIe port. The other includes a single Metis unit with an M.2 interface, a space-efficient alternative to PCIe that is often used in low-power devices. Companies can run AI models on Metis using a software toolkit called Voyager SDK. It relies on an open-source tool called Apache TVM to optimize customer algorithms for the chip. Additionally, Axelera AI provides a collection of pre-packaged AI models called the Model Zoo. The company is currently working on a second-generation chip called Europa (pictured.) It can perform 629 trillion computations per second, or more than twice as many as Metis. The chip includes 8 AI-optimized cores, 16 central processing unit cores and 128 megabytes of memory. Axelera AI says that Europa can provide up to three times the performance per watt of competing products. According to the company, the chip will be particularly suitable for running computer vision models. An internal Axelera AI test determined that it can process more than 13,168 frames per second.